Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker Verification (SV).

SOTA method for self-supervised speaker verification leveraging a large-scale pretrained ASR model.

Tiny automatic differentiation (autodiff) engine for NumPy tensors implemented in Python.

A tiny neural network framework developed entirely from scratch in C++ and CUDA.

Implementation of SSL frameworks for Speaker & Language Recognition in Tensorflow / Keras.

Ray-tracer, written in C++, featuring different objects, lightings, textures and scene configurations.

My completely customizable personal website built with Gatsby and sourced from static markdown files.